© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 15475
    Prev
    Next
    INDEX
    Explanations

    phrases indicating quantity or emphasis in relation to entities or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     popularity
    -0.52
    énéral
    -0.48
     Ganze
    -0.47
     Nemesis
    -0.44
     Constitucional
    -0.43
    dotenv
    -0.42
     discretionary
    -0.41
    Palindrome
    -0.41
     nonetheless
    -0.41
     Mulher
    -0.40
    POSITIVE LOGITS
    Datuak
    1.00
    expandindo
    0.82
    DBNull
    0.80
    AndroidJUnit
    0.79
    adpleegd
    0.79
     propOrder
    0.77
    saraba
    0.77
    rungsseite
    0.76
    Portale
    0.76
    StoreMessageInfo
    0.76
    Activations Density 0.262%

    No Known Activations